Message-ID: <CAL+tcoBU+UD_8aXkJy95zNzFeOBMQvQE6jj9syiKvOh_wcLrcw@mail.gmail.com>
Date:   Fri, 21 Apr 2023 10:48:51 +0800
From:   Jason Xing <kerneljasonxing@...il.com>
To:     Paolo Abeni <pabeni@...hat.com>
Cc:     Jakub Kicinski <kuba@...nel.org>, peterz@...radead.org,
        tglx@...utronix.de, jstultz@...gle.com, edumazet@...gle.com,
        netdev@...r.kernel.org, linux-kernel@...r.kernel.org
Subject: Re: [PATCH 0/3] softirq: uncontroversial change

On Fri, Apr 21, 2023 at 1:34 AM Paolo Abeni <pabeni@...hat.com> wrote:
>
> Hi all,
> On Thu, 2022-12-22 at 14:12 -0800, Jakub Kicinski wrote:
> > Catching up on LWN I run across the article about softirq
> > changes, and then I noticed fresh patches in Peter's tree.
> > So probably wise for me to throw these out there.
> >
> > My (can I say Meta's?) problem is the opposite to what the RT
> > sensitive people complain about. In the current scheme once
> > ksoftirqd is woken no network processing happens until it runs.
> >
> > When networking gets overloaded - that's probably fair, the problem
> > is that we confuse latency tweaks with overload protection. We have
> > a needs_resched() in the loop condition (which is a latency tweak)
> > Most often we defer to ksoftirqd because we're trying to be nice
> > and let user space respond quickly, not because there is an
> > overload. But the user space may not be nice, and sit on the CPU
> > for 10ms+. Also the sirq's "work allowance" is 2ms, which is
> > uncomfortably close to the timer tick, but that's another story.
> >
> > We have a sirq latency tracker in our prod kernel which catches
> > 8ms+ stalls of net Tx (packets queued to the NIC but there is
> > no NAPI cleanup within 8ms) and with these patches applied
> > on 5.19 fully loaded web machine sees a drop in stalls from
> > 1.8 stalls/sec to 0.16/sec. I also see a 50% drop in outgoing
> > TCP retransmissions and ~10% drop in non-TLP incoming ones.
> > This is not a network-heavy workload so most of the rtx are
> > due to scheduling artifacts.
> >
> > The network latency in a datacenter is somewhere around neat
> > 1000x lower than scheduling granularity (around 10us).
> >
> > These patches (patch 2 is "the meat") change what we recognize
> > as overload. Instead of just checking if "ksoftirqd is woken"
> > it also caps how long we consider ourselves to be in overload,
> > a time limit which is different based on whether we yield due
> > to real resource exhaustion vs just hitting that needs_resched().
> >
> > I hope the core concept is not entirely idiotic. It'd be great
> > if we could get this in or fold an equivalent concept into ongoing
> > work from others, because due to various "scheduler improvements"
> > every time we upgrade the production kernel this problem is getting
> > worse :(
>
[...]
> Please allow me to revive this old thread.

Hi Paolo,

So good to hear this :)

>
> My understanding is that we want to avoid adding more heuristics here,
> preferring a consistent refactor.
>
> I would like to propose a revert of:
>
> 4cd13c21b207 softirq: Let ksoftirqd do its job
>
> the its follow-ups:
>
> 3c53776e29f8 Mark HI and TASKLET softirq synchronous
> 0f50524789fc softirq: Don't skip softirq execution when softirq thread is parking

More than this, I list some related patches mentioned in the above
commit 3c53776e29f8:
1ff688209e2e ("watchdog: core: make sure the watchdog_worker is not deferred")
8d5755b3f77b ("watchdog: softdog: fire watchdog even if softirqs do
not get to run")
217f69743681 ("net: busy-poll: allow preemption in sk_busy_loop()")

>
> The problem originally addressed by 4cd13c21b207 can now be tackled
> with the threaded napi, available since:
>
> 29863d41bb6e net: implement threaded-able napi poll loop support
>
> Reverting the mentioned commit should address the latency issues
> mentioned by Jakub - I verified it solves a somewhat related problem in
> my setup - and reduces the layering of heuristics in this area.

Sure, it is. I also can verify its usefulness in the real workload.
Some days ago I also sent a heuristics patch [1] that can bypass the
ksoftirqd if the user chooses to mask some type of softirq. Let the
user decide it.

But I observed that if we mask some softirqs, or we can say,
completely revert the commit 4cd13c21b207, the load would go higher
and the kernel itself may occupy/consume more time than before. They
were tested under the similar workload launched by our applications.

[1]: https://lore.kernel.org/all/20230410023041.49857-1-kerneljasonxing@gmail.com/

>
> A refactor introducing uniform overload detection and proper resource
> control will be better, but I admit it's beyond me and anyway it could
> still land afterwards.

+1

Thanks,
Jason
>
> Any opinion more then welcome!
>
> Thanks,
>
> Paolo
>

Powered by blists - more mailing lists